bedrock

A project workspace that keeps important context in a `bedrock` folder, including project memory, current work, and human-readable views.

In plain words
What is it for?
Use it to organize project knowledge, track what matters now, record decisions, and update shared context after meaningful work.
Why use it?
It gives coding agents a consistent place to find project status and relevant background instead of relying on scattered files or past conversations.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/robotaitai/project-bedrock/bedrock
Clone the repo
git clone --depth 1 https://github.com/robotaitai/project-bedrock

Made for: Cursor.

Per session 364 This file is loaded in full into every session.
When invoked 364 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00364 $0.00364
Opus 5 $0.00182 $0.00182
Sonnet 5 $0.00073 $0.00073
Haiku 4.5 $0.00036 $0.00036

Measured 3d ago against content hash d9fe3a351286, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bedrock scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/bedrock.mdc · 44 lines

What it actually says

This project uses bedrock as a small project cockpit. All project context lives in ./bedrock/.

Project cockpit

  • Memory/ = what the project knows
  • Work/ = what matters now
  • Views/ = generated human inspection views

Legacy folders such as History/, Evidence/, Outputs/, or Sessions/ may still exist for compatibility. They are not the main user-facing model.

On session start

  1. Read ./bedrock/STATUS.md
  2. If onboarding: pending, read AGENTS.md and follow First-Time Onboarding
  3. If onboarding: complete, read ./bedrock/Memory/PROJECT.md
  4. Read ./bedrock/Work/NOW.md
  5. Load only the relevant Memory branches for the task

After meaningful work

  • Run /memory-update to update the project cockpit

How Memory is split

Memory is organized per area, one doc per subsystem:

  • Memory/<area>.md = everything durable about that area (navigation, perception, auth, billing, ...). If work touches an area with no doc yet, create it.
  • Memory/decisions.md = dated rationale for choices, not the design itself
  • Memory/PROJECT.md = cross-area overview only; it links to the area docs

Name areas after the project's own functional layers, not its hardware or file layout, so cross-cutting subsystems get a home instead of being scattered.

When the context window is getting long

  • Run /compact-context to save the project cockpit and reset context
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 44 lines · 364 tokens per session scan A d9fe3a351286

Subscribe to this mod's changes

bedrock is a cursor rule published in the GitHub repository robotaitai/project-bedrock (44 stars, last pushed 13d ago), licensed MIT. It adds 364 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.